Deep learning-based image quality assessment for optical coherence tomography macular scans: a multicentre study.

AIMS: To develop and externally test deep learning (DL) models for assessing the image quality of three-dimensional (3D) macular scans from Cirrus and Spectralis optical coherence tomography devices. METHODS: We retrospectively collected two data sets including 2277 Cirrus 3D scans and 1557 Spectralis 3D scans, respectively, for training (70%), fine-tuning (10%) and internal validation (20%) from electronic medical and research records at The Chinese University of Hong Kong Eye Centre and the Hong Kong Eye Hospital. Scans with various eye diseases (eg, diabetic macular oedema, age-related macular degeneration, polypoidal choroidal vasculopathy and pathological myopia), and scans of normal eyes from adults and children were included. Two graders labelled each 3D scan as gradable or ungradable, according to standardised criteria. We used a 3D version of the residual network (ResNet)-18 for Cirrus 3D scans and a multiple-instance learning pipline with ResNet-18 for Spectralis 3D scans. Two deep learning (DL) models were further tested via three unseen Cirrus data sets from Singapore and five unseen Spectralis data sets from India, Australia and Hong Kong, respectively. RESULTS: In the internal validation, the models achieved the area under curves (AUCs) of 0.930 (0.885-0.976) and 0.906 (0.863-0.948) for assessing the Cirrus 3D scans and Spectralis 3D scans, respectively. In the external testing, the models showed robust performance with AUCs ranging from 0.832 (0.730-0.934) to 0.930 (0.906-0.953) and 0.891 (0.836-0.945) to 0.962 (0.918-1.000), respectively. CONCLUSIONS: Our models could be used for filtering out ungradable 3D scans and further incorporated with a disease-detection DL model, allowing a fully automated eye disease detection workflow.

Association between deep learning measured retinal vessel calibre and incident myocardial infarction in a retrospective cohort from the UK Biobank.

BACKGROUND: Cardiovascular disease is a leading cause of global death. Prospective population-based studies have found that changes in retinal microvasculature are associated with the development of coronary artery disease. Recently, artificial intelligence deep learning (DL) algorithms have been developed for the fully automated assessment of retinal vessel calibres. METHODS: In this study, we validate the association between retinal vessel calibres measured by a DL system (Singapore I Vessel Assessment) and incident myocardial infarction (MI) and assess its incremental performance in discriminating patients with and without MI when added to risk prediction models, using a large UK Biobank cohort. RESULTS: Retinal arteriolar narrowing was significantly associated with incident MI in both the age, gender and fellow calibre-adjusted (HR=1.67 (95% CI: 1.19 to 2.36)) and multivariable models (HR=1.64 (95% CI: 1.16 to 2.32)) adjusted for age, gender and other cardiovascular risk factors such as blood pressure, diabetes mellitus (DM) and cholesterol status. The area under the receiver operating characteristic curve increased from 0.738 to 0.745 (p=0.018) in the age-gender-adjusted model and from 0.782 to 0.787 (p=0.010) in the multivariable model. The continuous net reclassification improvements (NRIs) were significant in the age and gender-adjusted (NRI=21.56 (95% CI: 3.33 to 33.42)) and the multivariable models (NRI=18.35 (95% CI: 6.27 to 32.61)). In the subgroup analysis, similar associations between retinal arteriolar narrowing and incident MI were observed, particularly for men (HR=1.62 (95% CI: 1.07 to 2.46)), non-smokers (HR=1.65 (95% CI: 1.13 to 2.42)), patients without DM (HR=1.73 (95% CI: 1.19 to 2.51)) and hypertensive patients (HR=1.95 (95% CI: 1.30 to 2.93)) in the multivariable models. CONCLUSION: Our results support DL-based retinal vessel measurements as markers of incident MI in a predominantly Caucasian population.

Performance of Artificial Intelligence in Detecting Diabetic Macular Edema From Fundus Photography and Optical Coherence Tomography Images: A Systematic Review and Meta-analysis.

BACKGROUND: Diabetic macular edema (DME) is the leading cause of vision loss in people with diabetes. Application of artificial intelligence (AI) in interpreting fundus photography (FP) and optical coherence tomography (OCT) images allows prompt detection and intervention. PURPOSE: To evaluate the performance of AI in detecting DME from FP or OCT images and identify potential factors affecting model performances. DATA SOURCES: We searched seven electronic libraries up to 12 February 2023. STUDY SELECTION: We included studies using AI to detect DME from FP or OCT images. DATA EXTRACTION: We extracted study characteristics and performance parameters. DATA SYNTHESIS: Fifty-three studies were included in the meta-analysis. FP-based algorithms of 25 studies yielded pooled area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of 0.964, 92.6%, and 91.1%, respectively. OCT-based algorithms of 28 studies yielded pooled AUROC, sensitivity, and specificity of 0.985, 95.9%, and 97.9%, respectively. Potential factors improving model performance included deep learning techniques, larger size, and more diversity in training data sets. Models demonstrated better performance when validated internally than externally, and those trained with multiple data sets showed better results upon external validation. LIMITATIONS: Analyses were limited by unstandardized algorithm outcomes and insufficient data in patient demographics, OCT volumetric scans, and external validation. CONCLUSIONS: This meta-analysis demonstrates satisfactory performance of AI in detecting DME from FP or OCT images. External validation is warranted for future studies to evaluate model generalizability. Further investigations may estimate optimal sample size, effect of class balance, patient demographics, and additional benefits of OCT volumetric scans.

Development and evaluation of two brief digital health promotion game booths utilizing augmented reality and motion detection to promote well-being at a gerontechnology summit in Hong Kong.

Background: The acceleration of population aging calls for simple and effective interventions catered for older people. Gerontechnology, the combination of gerontology and technology, can promote quality of life in older adults. However, public health-related events incorporating information communication technology (ICT) for older people have seldom been evaluated. Objective: We reported the development and evaluation of two simple and brief digital health promotion games hosted at the annual Hong Kong Gerontech and Innovation Expo cum Summit (GIES) in 2018 and 2019 to promote well-being. Methods: Two game booths (Dinosaur Augmented Reality photo-taking in 2018, Sit-and-Stand fitness challenge in 2019) were designed by our interdisciplinary team. Four gaming technologies were employed: augmented reality, chroma key (green screen), motion detection and 3D modeling. Immediately after the game, we administered a brief questionnaire survey to assess participant satisfaction, happiness and perceived benefits, and collected qualitative data through observations and informal interviews. Results: Majority of 1,186 and 729 game booth participants in 2018 and 2019, respectively, were female (73.4% and 64.7%) and older adults (65.5 and 65.2%). Overall satisfaction toward the game booths was high (4.64 ± 0.60 and 4.54 ± 0.68 out of 5), with females and older adults reporting higher scores. Average personal and family happiness of participants in 2018 were 8.2 and 8.0 (out of 10). 90.3 and 18.4% of participants in 2019 chose one or more personal (e.g. enhance healthy living habits 62.4%, enhance personal happiness 61.6%) and family (e.g. enhance family happiness 15.6%, improve family relationships 10.8%) benefits of the game booth, respectively. Participants showed enthusiasm toward the technologies, and pride in their physical abilities in the fitness challenge. Conclusion: Our report on the development and evaluation of brief game interventions with ICT showed high satisfaction and immediate perceived benefits in community participants. Females and older adults reported higher satisfaction. Simple tools measuring happiness and perceived benefits showed positive results. Older adults were receptive and enthusiastic about the new technologies. Our findings can inform researchers and organizers of similar events. More research on simple and enjoyable ICT interventions is needed to attract older adults and promote their well-being. Trial registration: The research protocol was registered at the National Institutes of Health (Identifier number: NCT03960372) on May 23, 2019.

Process Evaluation and Experience Sharing on Utilizing Information Communication Technologies and Digital Games in a Large Community Family Health Event: Hong Kong Jockey Club SMART Family-Link Project.

Background: Information communication technologies (ICT) are increasingly used in health promotion, but integration is challenging and involves complex processes. Large community health promotion events are often held but the experiences and processes have rarely been evaluated and published. No reports have described and systematically evaluated an ICT-supported health promotion event using digital games. Objective: We evaluated the development and implementation of a large community family health promotion event with ICT integration to promote family happiness with collaboration between academia (The University of Hong Kong) and the social (family) service sector, and collected feedback from participants and social service workers. Methods: We (i) conducted a systematic process evaluation, (ii) administered an on-site questionnaire survey on participant satisfaction and feedback, and (iii) collected post-event qualitative feedback from social workers on using new technologies, digital game design and overall experiences. Results: Fourteen digital games were designed and run in booths at the event by 12 non-governmental social service organizations and academia. Four gaming technologies were utilized: chroma key (green screen), somatosensory (kinect and leap motion techniques), augmented reality and virtual reality. 1,365 participants joined the event, in which 1,257 from 454 families were recruited and pre-registered through 12 NGOs. About 39.3% were male and more than half (53.3%) were aged 18 years and above. About 3,487 game booth headcounts were recorded. Games using virtual reality, kinect motion and green screen technologies were most liked. The average game satisfaction score was high (4.5 out of 5). Social service workers reported positive experiences with using new technologies in health promotion, and interests in future collaborations involving more ICT. Conclusions: Our systematic evaluation showed successful integration of ICT components in the health promotion event. This event, most likely the first of its kind, served as a capacity building and knowledge transfer platform for interdisciplinary co-sharing and co-learning of new technologies. It provided a solid foundation for further academic and social service partnerships and should be a useful model for similar community events and their evaluation. Further development and integration of ICT for health promotion among social service organizations with comprehensive evaluation are warranted.

BALSA: integrated secondary analysis for whole-genome and whole-exome sequencing, accelerated by GPU.

This paper reports an integrated solution, called BALSA, for the secondary analysis of next generation sequencing data; it exploits the computational power of GPU and an intricate memory management to give a fast and accurate analysis. From raw reads to variants (including SNPs and Indels), BALSA, using just a single computing node with a commodity GPU board, takes 5.5 h to process 50-fold whole genome sequencing (∼750 million 100 bp paired-end reads), or just 25 min for 210-fold whole exome sequencing. BALSA's speed is rooted at its parallel algorithms to effectively exploit a GPU to speed up processes like alignment, realignment and statistical testing. BALSA incorporates a 16-genotype model to support the calling of SNPs and Indels and achieves competitive variant calling accuracy and sensitivity when compared to the ensemble of six popular variant callers. BALSA also supports efficient identification of somatic SNVs and CNVs; experiments showed that BALSA recovers all the previously validated somatic SNVs and CNVs, and it is more sensitive for somatic Indel detection. BALSA outputs variants in VCF format. A pileup-like SNAPSHOT format, while maintaining the same fidelity as BAM in variant calling, enables efficient storage and indexing, and facilitates the App development of downstream analyses. BALSA is available at: http://sourceforge.net/p/balsa.